How to Use the Churnkey MCP in Vercel AI SDK

Q: Can I filter which Churnkey tools are available in my Vercel AI SDK app?

Yes. When you pass the tools to generateText or streamText, you can provide a filtered list. You might expose read-only tools like getsessionaggregates to a dashboard, but reserve deletecustomergdprdata for an admin-only interface.

Q: What's the setup for connecting Churnkey to the Vercel AI SDK?

It's straightforward. You'll install @ai-sdk/mcp, create a client with your Vinkius endpoint URL, and then call mcpClient.tools(). The resulting tool definitions are ready to be passed directly into the AI SDK's generation functions.

Stream Churnkey retention data directly into your React components. Build live dashboards with the Vercel AI SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Churnkey MCP to Vercel AI SDK

Create your Vinkius account to connect Churnkey to Vercel AI SDK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Churnkey with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live-Stream Cancellation Data

Your app can now show a live feed of cancellation attempts as they happen. Use the Vercel AI SDK to stream results from `list_retention_sessions` directly into your UI, updating a table or list without a page refresh. Users see the data appear in real time. When a user clicks on a session, you can instantly fetch and display the full context. The `get_retention_session_details` tool gives you the exit survey responses and metadata, streaming it all into view. It's a much better experience than a loading spinner.

Build Real-Time Retention Dashboards

Stop waiting for batch jobs to update your metrics. With the Vercel AI SDK, you can build a dashboard that pulls live numbers from `get_session_aggregates`. Watch trends in cancellation reasons or session outcomes as they develop. This also works for individual customer views. When your support team pulls up a customer record, your app can call `list_customer_retention_history` to show every interaction they've had with the cancellation flow. The history streams right into the page.

Interactive Tools for Your Vercel AI SDK App

Build a secure, internal GDPR compliance portal for your team. Your UI can use `get_customer_gdpr_data` to generate a data export on the fly, or `delete_customer_gdpr_data` to process a deletion request. The AI SDK handles the tool call, you just build the button. You can also give your team a simple interface for updating billing information. Connect a form to the `update_billing_contacts` tool. Your agent makes the API call to Churnkey, and your UI can show a success message the moment it's done.

Setup guide

Set up Churnkey MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Churnkey tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Churnkey transactions",
});

console.log(text);
await mcpClient.close();

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Churnkey. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Churnkey now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Churnkey MCP in Vercel AI SDK

The Churnkey MCP server's tools return data that the Vercel AI SDK can process as a stream. When your app calls a tool like `list_retention_sessions`, the results are fed into your UI component by component, not all at once. This makes your app feel much faster.

Yes. When you pass the tools to `generateText` or `streamText`, you can provide a filtered list. You might expose read-only tools like `get_session_aggregates` to a dashboard, but reserve `delete_customer_gdpr_data` for an admin-only interface.

It's straightforward. You'll install `@ai-sdk/mcp`, create a client with your Vinkius endpoint URL, and then call `mcpClient.tools()`. The resulting tool definitions are ready to be passed directly into the AI SDK's generation functions.

Yes, if you secure it properly. Your frontend should be an internal tool with strong authentication. The MCP connection itself is secure, but you're responsible for making sure only authorized users can trigger sensitive actions like `delete_customer_gdpr_data`.

The server processes customer identifiers, billing contact information, and cancellation session data like survey responses. All data is transmitted over HTTPS and handled within Vinkius's ephemeral, zero-trust sandbox. Your Vinkius endpoint token authenticates every request.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript